updated README

.gitignore

@@ -1,6 +1,132 @@
+# Custom .gitignore stuff
 package/key/
 *.jpg
 *.png
 *.jpeg
 *.nef
-*.xmp
+*.xmp
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

README.md

@@ -0,0 +1,9 @@
+# photo-tagging
+
+## What is this repository?
+
+This repository is for a interesting project involving Google's Vision API and support for automatic photo tagging, with support for Adobe's XMP metadata and other file property based metadata.
+
+## How does it work?
+
+This application is built in Python and utilizes the `google-cloud` python module. Install using `pip install google-cloud`. A key should be provided by google in a `.json` file, insert this at `./package/key/photo_tagging_service.json`.

main.py

@@ -3,5 +3,11 @@ from package import app
 
 os.environ["GOOGLE_APPLICATION_CREDENTIALS"]=os.path.join(sys.path[0], 'package', 'key', 'photo_tagging_service.json')
 
-if __name__ == "__main__":
-    sys.exit(app.run())
+# if __name__ == "__main__":
+#     sys.exit(app.run())
+
+import exif
+path = 'E:\\Photography\\Colorado 2019\\DSC_7960.jpg'
+image = exif.Image(open(path, 'rb'))
+print(image.artist)
+print(dir(image))

package/app.py

@@ -1,8 +1,8 @@
-import io, sys, os, time, rawpy, imageio, progressbar
-from google.cloud import vision
+import io, sys, os, time, rawpy, imageio, progressbar, shutil, iptcinfo3
 from google.cloud.vision import types
+from google.cloud import vision
+from package import xmp
 from PIL import Image
-from package.xmp import writeTags
 
 # The name of the image file to annotate
 input_path = os.path.join(sys.path[0], 'package', 'processing', 'input')
@@ -36,7 +36,7 @@ def process_file(file_name, xmp):
         image.thumbnail(size, resample=Image.ANTIALIAS)
         image.save(file_path, format='jpeg', optimize=True, quality=quality)
 
-    base = os.path.splitext(file_name)[0]
+    base, ext = os.path.splitext(file_name)
     temp_file_path = os.path.join(temp_path, base + '.jpeg')
 
     try:
@@ -64,11 +64,20 @@ def process_file(file_name, xmp):
         response = client.label_detection(image=image)
         labels = [label.description for label in response.label_annotations]
         print('\tLabels: {}'.format(', '.join(labels)))
-
-        print('\tWriting {} tags to output folder...')
-        writeTags(os.path.join(input_path, xmp), os.path.join(output_path, xmp), labels)
-        print('\tMoving associated original image file...')
-        os.rename(os.path.join(input_path, file_name), os.path.join(output_path, file_name))
+        if ext == '.NEF':
+            print('\tWriting {} tags to output XMP...'.format(len(labels)))
+            xmp.writeXMP(os.path.join(input_path, xmp), os.path.join(output_path, xmp), labels)
+        else:
+            print('\tWriting {} tags to output {}'.format(len(labels), ext[1:].upper()))
+            info = iptcinfo3.IPTCInfo(os.path.join(input_path, xmp))
+            info['keywords'].extend(labels)
+            info.save()
+            # Remove the strange ghost file
+            os.remove(os.path.join(input_path, xmp) + '~')
+            print('\tMoving associated original image file...')
+        # Copy dry-run
+        shutil.copy2(os.path.join(input_path, file_name), os.path.join(output_path, file_name))
+        # os.rename(os.path.join(input_path, file_name), os.path.join(output_path, file_name))
         
     except:
         _cleanup()

package/xmp.py

@@ -1,14 +1,13 @@
 # from libxmp import file_to_dict
 import os, sys, re
 
-ext_filter = lambda file : file.endswith('.NEF')
 mainPattern = r'<dc:subject>\n\s+<rdf:Bag>\n(?:     <rdf:li>.+<\/rdf:li>\n)*\s+<\/rdf:Bag>\n\s+<\/dc:subject>\n'
 subPattern = r'<rdf:li>(.*)</rdf:li>\n'
 subFormatPattern = '     <rdf:li>{}</rdf:li>\n'
 
-def writeTags(inputPath, outputPath, tags):
+# Write tags to an XMP file, using regex patterns
+def writeXMP(inputPath, outputPath, tags):
     data = open(inputPath, 'r').read()
-
     # Detect and find the <dc:Subject: part
     match = re.search(mainPattern, data)
     # If it's not found, we just add the tags area right below the creator tag
@@ -17,17 +16,13 @@ def writeTags(inputPath, outputPath, tags):
         look = data.find('</dc:creator>') + 13
         data = data[:look] + addition + data[look:]
         match = re.search(mainPattern, data)
-
     # Get last matching tag
     submatch = None
     for submatch in re.finditer(subPattern, match.group(0)):
         pass
-
     # Calculate very end
     spanend = match.span()[0] + (submatch.span()[1] if submatch else 0)
-    
    # add tags to end
     data = data[:spanend] + ''.join(subFormatPattern.format(tag) for tag in tags) + data[spanend:]
-    
     # Write file to disk
     open(outputPath, 'w+').write( data)